3

我想将文档图像转换为 XML，并导出在页面中找到某个单词的位置。为了访问边界框信息，可以使用 tesseract 的布局分析：

 tess.SetImage(...); 
 tess.SetPageSegMode( tesseract::PSM_AUTO_OSD); 
 tesseract::PageIterator* it = tess.AnalyseLayout(); 
 while(it->Next(tesseract::RIL_WORD)
 {
      int top, bottom, left, right; 
      it->BoundingBox(tesseract::RIL_WORD, &left, &top, &right, &bottom); 

 }

然而，那时我不知道边界框的实际内容，通过执行以下代码，对当前图像执行 OCR，因此text包含页面的整个文本。

 tess.Recognize(0); 
 std::string text = tess.GetUTF8Text();

目前我暂时将所有边界框存储在vector. 对于每个框，我从原始框中剪切出一个子图像，并对每个边界框执行 OCR。基本上这是可行的，但是当我将结果与 Tesseract 命令行工具进行比较时，会发生更多的 OCR 错误。

因此，我想知道如何逐字遍历 OCR 结果并获得相应的边界框。

4

2 回答 2

2 
tess.Recognize(0);

PAGE_RES_IT resultIter(page_res_);

for (resultIter.start_page(false); resultIter.block() != NULL; resultIter.forward()) 
{

            WERD_RES* wordResult = resultIter.word();
            WERD_CHOICE* word = wordResult->best_choice;

            TBOX& box = wordResult->word->bounding_box();
}
于 2012-07-11T12:25:38.887 回答
0 
NSString *retText = @"";
tesseract::ResultIterator *ri = tess.GetIterator();
tesseract::PageIteratorLevel level = tesseract::RIL_WORD;

if (ri != 0) {
do {
  const char *word = ri->GetUTF8Text(level);
  float conf = ri->Confidence(level);
  int x1, y1, x2, y2;
  ri->BoundingBox(level, &x1, &y1, &x2, &y2);

  if (word) {
    printf("word: '%s';  \tconf: %.2f; BoundingBox: %d,%d,%d,%d;\n", word,
           conf, x1, y1, x2, y2);

    NSString *temp =
        [NSString stringWithCString:word encoding:NSUTF8StringEncoding];
    retText = [NSString stringWithFormat:@"%@ %@", retText, temp];
    retText = [retText stringByReplacingOccurrencesOfString:@"[\\\""
                                                 withString:@""];
    retText = [retText stringByReplacingOccurrencesOfString:@"\n\n"
                                                 withString:@""];

    UIBezierPath *path = [UIBezierPath bezierPath];

    [path moveToPoint:CGPointMake(x1, y1)];
    [path addLineToPoint:CGPointMake(x2, y1)];
    [path addLineToPoint:CGPointMake(x2, y2)];
    [path addLineToPoint:CGPointMake(x1, y2)];
    [path addLineToPoint:CGPointMake(x1, y1)];

    CAShapeLayer *shapeLayer = [CAShapeLayer layer];
    shapeLayer.path = [path CGPath];
    shapeLayer.strokeColor = [[UIColor blueColor] CGColor];
    shapeLayer.lineWidth = 3.0;
    shapeLayer.fillColor = [[UIColor clearColor] CGColor];

    [self.scrollView.layer addSublayer:shapeLayer];

    delete[] word;
  }
} while (ri->Next(level));
}
于 2014-08-13T03:47:41.647 回答